Changhun Lee
11 papers · 2021–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (32) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Renaissance Researcher (6)
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(61)
Top co-authors
Research topics
Machine Learning
(11)
Deep Learning
(10)
Artificial Intelligence
(8)
Application Areas
(8)
Core AI
(8)
Learning Types
(5)
Optimization & Theory Β· Machine Learning
(4)
Natural Language Processing
(3)
Models
(3)
Optimization & Theory Β· Deep Learning
(3)
Techniques
(3)
Architectures
(2)
Core Methods
(2)
Resources & Methods
(2)
Computer Vision
(1)
Keywords
model compression
(4)
large language model
(4)
language model
(2)
binary neural network
(2)
parameter-efficient fine-tuning
(2)
mixed-precision quantization
(2)
personalized generation
(1)
attention mechanism
(1)
post-training quantization
(1)
text style transfer
(1)
neural network optimization
(1)
efficient computing
(1)
reinforcement learning from human feedback
(1)
early exit
(1)
language model alignment
(1)
reinforcement learning
(1)
state space model
(1)
generative model
(1)
text-to-image generation
(1)
higher-order statistics
(1)
Papers
DreamCatcher: Efficient Multi-Concept Customization via Representation Finetuning
WACV 2026
AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models
EMNLP 2025
PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality
EMNLP 2025
PTQ4VM: Post-Training Quantization for Visual Mamba
WACV 2025
SEAL: Scaling to Emphasize Attention for Long-Context Retrieval
ACL 2025
OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models
AAAI 2024
QEFT: Quantization for Efficient Fine-Tuning of LLMs
EMNLP 2024
Repurformer: Transformers for Repurposing-Aware Molecule Generation
ACL 2024
Towards Pareto-Efficient RLHF: Paying Attention to a Few High-Reward Samples with Reward Dropout
EMNLP 2024
INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold
ICCV 2023
Improving Accuracy of Binary Neural Networks Using Unbalanced Activation Distribution
CVPR 2021